AI Observatory / Model Radar Minimax / minimax/minimax-m2

MiniMax: MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

196,608 Context
196,608 Max output
$0.26 / 1M Prompt price
2025-10-23 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider Minimax Input modalities text
Output modalities text Prompt price $0.26 / 1M
Completion price $1.00 / 1M Request price N/A
Context length 196,608 Max completion tokens 196,608
Supported parameters frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Best for minimax/minimax-m2

MiniMax: MiniMax M2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Deep analysis Coding workflows High-volume usage tool-capable low-cost
03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.